基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
AI 모델 탐색 85005
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
> [!NOTE] > **Please credit if you build on this.** If you redistribute, quantize, fine-tune, serve, benchmark, or write about this model, a line like > _"Based on `dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8`"_ > in your model card or write-up means a lot. Thank you. > [!TIP] > **Quantizing this FP8 checkpoint directly won't give the best quality.** Low-bit quants that are naively derived from these weights carry quantization error on top of the abliteration edit, and compliance can regress at low bits. For a proper low-bit release, redo the abliteration pipeline on the target precision rather than quantizing this bundle after the fact. (The sibling EXL3 2.9 bpw UNCENSORED is built that way end-to-end.) > [!IMPORTANT] > Native FP8 (e4m3) with ue8m0 block scales + FP4 MoE experts. 1M-token context. Multimodal > (image + video) + tool calling + reasoning-effort tiers (`low` / `high` / `max`) all preserved. > **Recommended sampling:** `temperature=1.0`, `top_p=1.0`, `max_tokens ≥ 256K` (heavy reasoner).
번역 대기 중 · 원문 표시
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
DeepSeek-V4.1-Flash-UNCENSORED-FP8
dealignai**Abliterated · No guardrails · Native FP8 · 1M-token context · Vision + tools · Reasoning-max default** **Proprietary weight-level abliteration** developed by the dealignai research team. No custom `model.py`, no runtime hooks, no steering vectors — it's a standard checkpoint that loads exactly like the base model. The refusal circuitry is surgically removed while every capability-critical component (routed experts, Engram memory, CSA2 sparse attention, DSpark draft head, vision tower, router gates, norms, embeddings) is preserved byte-identical to the base. Every response 4-tier graded (HARD_REF / SOFT_RED / HEDGE / COMPLY), with reasoning-trace verification at effort=max.
번역 대기 중 · 원문 표시
DeepSeek-V4-Flash-0731-CRACK-NVFP4
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
DeepSeek-V4-Flash-0731-JANG-CRACK
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
Gemma-4-26B-A4B-JANG_4M-CRACK
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
Gemma-4-31B-JANG_4M-CRACK
dealignai**Abliterated Gemma 4 31B Dense — 60 layers, hybrid sliding/global attention, multimodal VL** > **Recommended: Run in vMLX** for best experience including thinking mode support, repetition penalty, and vision capabilities. - **Improved abliteration**: Higher quality refusal vector extraction - **Thinking-ON stability**: Clean thinking cycle — no more degenerate loops - **Same compliance**: 93.7% HarmBench - **Architecture-aware**: Tuned for Gemma 4's hybrid attention design
번역 대기 중 · 원문 표시
Gemma-4-31B-JANG_4M-Uncensored
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
GLM-5.3-ABLITERATED-NVFP4
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
GLM-5.3-CYBERSECURITY-FP8
dealignaia **CRACK** release by dealignai · Twitter @dealignai > [!IMPORTANT] > **Runtime notes** — field-tested on 8× DGX Spark GB10 by @0xMagnus (discussion): > > - **`reasoning_effort` only honors `"low"` and `"high"`.** Every other value — `off`, `medium`, `max`, unset, or an unquoted YAML `off:` (parses as boolean `false`) — falls through to `max`. There is no way to disable reasoning on this checkpoint; pass `"low"` for minimum. > - **On FP8, prefer `low` for agent / tool-loop use.** At `high`/`max` the model can spend the whole `max_tokens` budget inside ` ` and return zero answer tokens (finish=`length`); sampling params (temp 0 + rep 1.05, temp 0.7 / top-p 0.95) do not rescue it. It is budget exhaustion, not a loop. If you must run `high`/`max`, give `max_tokens ≥ 8000`. > - **Reasoning text is in `message.reasoning`**, not `message.reasoning_content`. > - **MTP:** non-functional on stock vLLM, but reported working on ciprianveg's B12X sparse-MLA vLLM fork with `--draft-attention-backend B12X_MLA_SPARSE` (+48% decode on coding prompts). > - **1M context via decode-context-parallel is closed** on `glm_moe_dsa` in vLLM today (DSA indexer `k_cache` is replicated across DCP ranks while MLA KV is sharded → `page size is not divisible by target page size and cannot be padded` for `fp8_ds_mla`). Practical TP8 H200 ceiling: ~131K w/MTP, ~160K w/o. Pipeline-parallel (PP2 × TP4) profiles fine, but the MTP draft does not implement `SupportsPP`. **This is a CYBERSECURITY-DOMAIN CRACK of GLM-5.3-FP8 — not a general-purpose uncensor.**
번역 대기 중 · 원문 표시
GLM-5.3-Flash-CYBERSECURITY-W4A16
dealignai> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build
번역 대기 중 · 원문 표시
GLM-5.3-Flash-UNCENSORED-FP8
dealignai> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build. Set > `fps`, which every build honours. > - **Pixel controls: use `mm_processor_kwargs.max_image_tokens` / `min_image_tokens`.** > `max_pixels`, `min_pixels`, `size` and `detail` return HTTP 200 and
번역 대기 중 · 원문 표시
GLM-5.3-Flash-UNCENSORED-NVFP4
dealignai> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build
번역 대기 중 · 원문 표시
GLM-5.3-UNCENSORED-FP8
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
GLM-5.3-UNCENSORED-NVFP4
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
GPT-OSS-120B-MLX-CRACK
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
Laguna-XS-2.1-CRACK-GGUF
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
MiMo-V2.6-Flash-RL-UNCENSORED
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
MiniCPM-V-4.7-1B-CRACK-GGUF
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
MiniCPM-V-4.7-35B-A3B-CRACK-GGUF
dealignaiRefusal-direction–ablated GGUF of `openbmb/MiniCPM-V-4.7-35B-A3B`, the 35B-A3B Qwen3.5-moe-text (hybrid GatedDeltaNet + Full-Attention + 256 routed experts + 1 shared expert) multimodal model. Surgery removes the model's refusal direction from **all three residual-stream writer tiers** of the Qwen3.5 hybrid architecture — the SSM output path is the critical tier that single-tier surgeries miss on this architecture. Multimodal (16× + 4× projectors) and DSpark speculative-decoding paths are preserved. HarmBench-240 (standard + contextual + copyright splits), MMLU-200 (balanced subjects, logit-eval), multi-turn 5-scenario coherence, harsh-10 hot categories. Multimodal verified on synthetic image (number `7342` + red square + blue circle).
번역 대기 중 · 원문 표시
MiniCPM5-2B-CRACK-JANG_8M
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
MiniMax-M2.5-UNCENSORED-JANG_2L
dealignai基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
일치하는 모델 없음
제공사, 분류, 입출력 조건을 조정하세요. 새 모델이 계속 등록됩니다.
좋은 모델, 명확한 비용.
월간 토큰 사용량으로 예상 API 비용을 비교하세요.
동일 채널의 기본 텍스트 토큰 요금 비교
수집된 백만 토큰당 USD 요금입니다. 캐시 할인, 구간 요금, 추가 추론 출력, 세금은 제외됩니다. 최신 요금은 출처에서 확인하세요.
이해하고 선택하세요
API 요금은 어떻게 비교하나요?+
입력, 출력, 캐시 요금을 구분하고 동일 작업량으로 비교하세요. 이미지, 음성, 영상은 개수, 시간, 해상도로 과금될 수 있습니다.
오픈 웨이트는 무료 상업 이용을 뜻하나요?+
반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 제한, 정책을 확인하세요. 자체 호스팅에는 연산 및 유지 비용도 듭니다.
1위 모델이 나에게 가장 적합한가요?+
순위는 작업, 버전, 평가 방식에 따라 다릅니다. 실제 업무로 정확도, 지연, 안정성, 비용을 비교하세요.